Constrained-Space Optimization and Reinforcement Learning for Complex Tasks.

Ya-Yen Tsai Bo Xiao Edward Johns Guang-Zhong Yang

Published in: IEEE Robotics Autom. Lett. (2020)

Keyphrases

reinforcement learning
complex domains
complex data
transfer learning
optimization algorithm
concave convex procedure

optimization process
optimization problems
low dimensional
action space
learning algorithm
real world

transferring knowledge
reinforcement learning agents
saddle point
machine learning
model free
complex environments

constrained optimization
function approximation
high level
global optimization
vector space
state space